jennifer-jy's picture
First Push
3f15abe verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.102818489074707,
"min": 2.102818489074707,
"max": 2.890317678451538,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 19985.1875,
"min": 19985.1875,
"max": 29653.171875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 4.85476016998291,
"min": -0.0963331013917923,
"max": 4.85476016998291,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 946.67822265625,
"min": -18.688621520996094,
"max": 946.67822265625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 16.022727272727273,
"min": 2.9545454545454546,
"max": 16.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 705.0,
"min": 130.0,
"max": 876.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 16.022727272727273,
"min": 2.9545454545454546,
"max": 16.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 705.0,
"min": 130.0,
"max": 876.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03475197182330791,
"min": 0.0341539622442196,
"max": 0.0394945477546219,
"count": 12
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03475197182330791,
"min": 0.0341539622442196,
"max": 0.0394945477546219,
"count": 12
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2917597937007104,
"min": 0.09663006418174314,
"max": 0.305335432675577,
"count": 12
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.2917597937007104,
"min": 0.09663006418174314,
"max": 0.305335432675577,
"count": 12
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 9.732096756000008e-06,
"min": 9.732096756000008e-06,
"max": 0.00027584400805199995,
"count": 12
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.732096756000008e-06,
"min": 9.732096756000008e-06,
"max": 0.00027584400805199995,
"count": 12
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.103244,
"min": 0.103244,
"max": 0.191948,
"count": 12
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.103244,
"min": 0.103244,
"max": 0.191948,
"count": 12
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00017187560000000014,
"min": 0.00017187560000000014,
"max": 0.004598205199999999,
"count": 12
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00017187560000000014,
"min": 0.00017187560000000014,
"max": 0.004598205199999999,
"count": 12
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1749436969",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749437380"
},
"total": 411.1192359500001,
"count": 1,
"self": 0.43023028100014926,
"children": {
"run_training.setup": {
"total": 0.024200774000064484,
"count": 1,
"self": 0.024200774000064484
},
"TrainerController.start_learning": {
"total": 410.66480489499986,
"count": 1,
"self": 0.3139371709992247,
"children": {
"TrainerController._reset_env": {
"total": 3.622845586999915,
"count": 1,
"self": 3.622845586999915
},
"TrainerController.advance": {
"total": 406.64791202800063,
"count": 18192,
"self": 0.3468765430025087,
"children": {
"env_step": {
"total": 286.25190700198686,
"count": 18192,
"self": 218.05365934999895,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.00784398099279,
"count": 18192,
"self": 1.2008253239857822,
"children": {
"TorchPolicy.evaluate": {
"total": 66.807018657007,
"count": 18192,
"self": 66.807018657007
}
}
},
"workers": {
"total": 0.19040367099512423,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 409.26378632499507,
"count": 18192,
"is_parallel": true,
"self": 217.91044436898937,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005744860000049812,
"count": 1,
"is_parallel": true,
"self": 0.004236458000150378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015084019998994336,
"count": 10,
"is_parallel": true,
"self": 0.0015084019998994336
}
}
},
"UnityEnvironment.step": {
"total": 0.04994758099996943,
"count": 1,
"is_parallel": true,
"self": 0.0005573550000690375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004032729999607909,
"count": 1,
"is_parallel": true,
"self": 0.0004032729999607909
},
"communicator.exchange": {
"total": 0.04691777400000774,
"count": 1,
"is_parallel": true,
"self": 0.04691777400000774
},
"steps_from_proto": {
"total": 0.0020691789999318644,
"count": 1,
"is_parallel": true,
"self": 0.00037314100006824447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00169603799986362,
"count": 10,
"is_parallel": true,
"self": 0.00169603799986362
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 191.3533419560057,
"count": 18191,
"is_parallel": true,
"self": 9.508512405997408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.361414292011887,
"count": 18191,
"is_parallel": true,
"self": 5.361414292011887
},
"communicator.exchange": {
"total": 146.44241436000243,
"count": 18191,
"is_parallel": true,
"self": 146.44241436000243
},
"steps_from_proto": {
"total": 30.041000897993968,
"count": 18191,
"is_parallel": true,
"self": 5.248429353003189,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.79257154499078,
"count": 181910,
"is_parallel": true,
"self": 24.79257154499078
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.04912848301126,
"count": 18192,
"self": 0.35907589401597306,
"children": {
"process_trajectory": {
"total": 26.92294787599542,
"count": 18192,
"self": 26.348921097995458,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5740267779999613,
"count": 4,
"self": 0.5740267779999613
}
}
},
"_update_policy": {
"total": 92.76710471299987,
"count": 12,
"self": 64.06822960099487,
"children": {
"TorchPPOOptimizer.update": {
"total": 28.698875112005,
"count": 1860,
"self": 28.698875112005
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.310001587437e-07,
"count": 1,
"self": 9.310001587437e-07
},
"TrainerController._save_models": {
"total": 0.08010917799992967,
"count": 1,
"self": 0.0007963460000155465,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07931283199991412,
"count": 1,
"self": 0.07931283199991412
}
}
}
}
}
}
}